feat: add minimax tts

relay/channel/minimax/adaptor.go

@@ -0,0 +1,130 @@
+package minimax
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/QuantumNous/new-api/relay/channel"
+	relaycommon "github.com/QuantumNous/new-api/relay/common"
+	"github.com/QuantumNous/new-api/relay/constant"
+	"github.com/QuantumNous/new-api/types"
+
+	"github.com/gin-gonic/gin"
+)
+
+type Adaptor struct {
+}
+
+func (a *Adaptor) ConvertGeminiRequest(*gin.Context, *relaycommon.RelayInfo, *dto.GeminiChatRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, req *dto.ClaudeRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
+	if info.RelayMode != constant.RelayModeAudioSpeech {
+		return nil, errors.New("unsupported audio relay mode")
+	}
+
+	voiceID := mapVoiceType(request.Voice)
+	speed := request.Speed
+	outputFormat := mapOutputFormat(request.ResponseFormat)
+
+	c.Set("response_format", outputFormat)
+
+	minimaxRequest := MiniMaxTTSRequest{
+		Model:        getTTSModel(info.OriginModelName),
+		Text:         request.Input,
+		VoiceID:      voiceID,
+		Speed:        speed,
+		OutputFormat: outputFormat,
+	}
+
+	// 同步扩展字段的厂商自定义metadata
+	if len(request.Metadata) > 0 {
+		if err := json.Unmarshal(request.Metadata, &minimaxRequest); err != nil {
+			return nil, fmt.Errorf("error unmarshalling metadata to minimax request: %w", err)
+		}
+	}
+
+	jsonData, err := json.Marshal(minimaxRequest)
+	if err != nil {
+		return nil, fmt.Errorf("error marshalling minimax request: %w", err)
+	}
+
+	// Debug: log the request structure
+	fmt.Printf("MiniMax TTS Request: %s\n", string(jsonData))
+
+	return bytes.NewReader(jsonData), nil
+}
+
+func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
+}
+
+func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
+	return GetRequestURL(info)
+}
+
+func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
+	channel.SetupApiRequestHeader(info, c, req)
+
+	if info.RelayMode == constant.RelayModeAudioSpeech {
+		req.Set("Content-Type", "application/json")
+		return nil
+	}
+
+	req.Set("Authorization", "Bearer "+info.ApiKey)
+	return nil
+}
+
+func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
+	if request == nil {
+		return nil, errors.New("request is nil")
+	}
+	return request, nil
+}
+
+func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
+	return nil, nil
+}
+
+func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
+	return request, nil
+}
+
+func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
+	return nil, errors.New("not implemented")
+}
+
+func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
+	return channel.DoApiRequest(a, c, info, requestBody)
+}
+
+func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
+	if info.RelayMode == constant.RelayModeAudioSpeech {
+		return handleTTSResponse(c, resp, info)
+	}
+
+	// For chat completions, just pass through the response
+	// MiniMax API is compatible with OpenAI format
+	return handleChatCompletionResponse(c, resp, info)
+}
+
+func (a *Adaptor) GetModelList() []string {
+	return ModelList
+}
+
+func (a *Adaptor) GetChannelName() string {
+	return ChannelName
+}